NodeBenchAI: Skill for Claude Code

.claude/skills/dep-tiptap-pm/SKILL.md

dep-tiptap-pm is a skill for Claude Code from HomenShum/NodeBenchAI. It costs 81 tokens per session (1,408 once invoked), scanned A, original, MIT.

A maintenance runbook for keeping the Tiptap package manager dependency at version 3.22.3. Tiptap is a text-editor framework, and the runbook documents a package-export problem in version 3.22.4.

In plain words
What is it for?
Use it when upgrading Tiptap or investigating a Vite build error saying that ./collab is not exported.
Why use it?
It prevents dependency updates from breaking builds when another package still expects the removed ./collab entry.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is HomenShum/NodeBenchAI's own configuration. It tells Claude Code how to work on NodeBenchAI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NodeBenchAI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/skills/dep-tiptap-pm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dep-tiptap-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-tiptap-pm.svg)](https://agentmods.dev/skills/homenshum/nodebenchai/dep-tiptap-pm)
Your own site
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/dep-tiptap-pm"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-tiptap-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01408
Opus 5 $0.00041 $0.00704
Sonnet 5 $0.00016 $0.00282
Haiku 4.5 $0.00008 $0.00141

Measured 6d ago against content hash 2bd3dba69e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dep-tiptap-pm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/dep-tiptap-pm/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@tiptap/pm pin runbook

Last verified

  • Working pin: 3.22.3 (held since 2026-04-26)
  • Known-bad version: 3.22.4 (drops ./collab export, breaks vite build)

Why we're pinned

@tiptap/[email protected] removed ./collab from its package.json exports map. Some transitive consumer in our dep graph still imports @tiptap/pm/collab — we couldn't find the importer with 87K-file grep across node_modules, suggesting either rolldown's transitive probing or a dynamic import we didn't catch.

The build error:

[rolldown:vite-resolve] Error:
"./collab" is not exported under the conditions
["module", "browser", "production", "import"] from package @tiptap/pm

This regression landed in PR #113 (minor-and-patch group bump that moved @tiptap/pm 3.13.0 → 3.22.4 alongside @blocknote/* 0.44 → 0.49). Hotfixed by PR #148.

Version-by-version ./collab history

Established by querying npm view @tiptap/pm@<v> exports:

Version range ./collab exported?
≤ 3.13.0 ✅ yes
3.14.0 – 3.21.0 ✅ yes
3.21.1 – 3.21.3 ❌ NO (interim removal)
3.22.0 – 3.22.3 ✅ yes (restored)
3.22.4 ❌ NO (final removal)

The pattern (remove → restore → remove again) suggests intentional deprecation. Don't expect 3.22.5+ to bring ./collab back.

Recipe (when an importer is finally identified)

Option A — fix the importer

If we can find the package importing @tiptap/pm/collab (likely candidates: @blocknote/core, @blocknote/react, @tiptap/extensions):

  1. Bump that package to a version that doesn't import ./collab (likely a newer minor that switched to importing from prosemirror-collab directly).
  2. Remove the @tiptap/pm pin in package.json (let it float to latest).
  3. Run npm install then npx vite build — should succeed.

Option B — replace prosemirror-collab import sites

If the importer is in OUR code (sometimes shows up after deeper grepping):

-import { collab } from "@tiptap/pm/collab"
+import { collab } from "prosemirror-collab"

prosemirror-collab is what @tiptap/pm/collab re-exported; the underlying package is unchanged.

Read the full file on GitHub · 105 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 105 lines · 81 tokens per session scan A 2bd3dba69e5d

Subscribe to this mod's changes

dep-tiptap-pm is a skill published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,408 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

convex-agents

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.

waynesutton/convexskills · 32 tokens

convex-agents

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 32 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens